Voice generation involves the creation of voices that best conform to supportive evidence, such as the structure of the skull, or the 3D image/scan of a face. Often, the supportive evidence may not have the information needed to generate every aspect of the voice signal, including language, content, style of delivery etc. This is especially true when the evidence is merely the image of a face or the structure of the skull. As such, there are many challenges associated with this process, each of which requires deeper consideration and different sets of approaches to address and solve.
One such challenge is that of rendering the correct intonation or prosody to the generated (or synthesized) voice signal. Of the many solutions we have explored for this, a good one seems to be that or using a “style of rendering” or prosody from an exemplar voice sample, rendered by a human, and “transferring” it to the generated voice signal. Note that in this case, the goal is to simply emulate the prosody -- the content of the generated signal may be different from that of the exemplar.
In the examples below, we show the results of one such mechanism that we have devised to transfer prosody from an exemplar (called a “token”) to the generate signal. The first set labeled “tokens” shows 5 exemplars from which we have attempted to “lift” the prosody alone. The next two sets of examples of the results of this process on signals that have the same linguistic content, and those that have different content (which is our goal). A paper describing our specific techniques is available at
Different prosodies are automatically factorized from the training dataset. Each of these factorized "prosodies" can then be tranfered to a test set.
Utterance content: My mother always took him to the town on a market day in a light gig.
Utterance content: So we never saw Dick any more.
Utterance content: You will be to visit me in prison with a basket of provisions, you will not refuse to visit me in prison?
The following shows some examples of prosody transfer, where the linguistic content of the reference utterance is different from that of the generated utterance. The prosody of reference utterance is transfered to the synthesized utterance.